© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92119
    Prev
    Next
    INDEX
    Explanations

    incursion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Panda
    -0.81
    aser
    -0.77
    ViewImports
    -0.71
     للمعارف
    -0.66
    antMatchers
    -0.64
    Παραπομπές
    -0.64
    Referències
    -0.58
    Panda
    -0.57
    קישורים
    -0.54
     mxArray
    -0.53
    POSITIVE LOGITS
    __(/*!
    0.68
    ionados
    0.58
     متعلقه
    0.57
     dependencies
    0.54
    []>
    0.52
     diaspora
    0.52
     Thule
    0.52
     Eugenia
    0.52
    nani
    0.51
     Limoges
    0.51
    Activations Density 1.603%

    No Known Activations